> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenAI Embedder

> Embed documents with OpenAIEmbedder. The default model is text-embedding-3-small.

`OpenAIEmbedder` uses the OpenAI Embeddings API. The default model is `text-embedding-3-small` with 1536 dimensions.

```python openai_embedder.py theme={null}
from agno.knowledge.embedder.openai import OpenAIEmbedder
from agno.knowledge.knowledge import Knowledge
from agno.vectordb.pgvector import PgVector

embedder = OpenAIEmbedder()
embedding = embedder.get_embedding(
    "The quick brown fox jumps over the lazy dog."
)

print(f"First values: {embedding[:5]}")
print(f"Dimensions: {len(embedding)}")

knowledge = Knowledge(
    vector_db=PgVector(
        db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
        table_name="openai_embeddings",
        embedder=embedder,
    ),
    max_results=2,
)

knowledge.insert(
    name="Fox fact",
    text_content="The quick brown fox jumps over the lazy dog.",
)
results = knowledge.search("Which animal jumps?")
print(results[0].content if results else "No results found")
```

## Model Dimensions

| Model | Default Dimensions |
| - | - |
| `text-embedding-3-small` | 1536 |
| `text-embedding-3-large` | 3072 |

Set `dimensions` to request a shorter vector from either `text-embedding-3` model. PgVector fixes the vector width when it creates a table. After changing the model or dimensions, use a new table name or drop and recreate the existing table before inserting the content again.

## Usage

<Snippet file="create-venv-step.mdx" />

**1. Set your API key**

```bash theme={null}
export OPENAI_API_KEY=your_openai_api_key_here
```

**2. Install dependencies**

```bash theme={null}
uv pip install -U agno openai pgvector psycopg sqlalchemy
```

<Snippet file="run-pgvector-step.mdx" />

**3. Run the example**

```bash theme={null}
python openai_embedder.py
```

## Developer Resources

* [OpenAIEmbedder reference](https://agno-v2.mintlify.site/reference/knowledge/embedder/openai.md)
* [OpenAI embeddings guide](https://developers.openai.com/api/docs/guides/embeddings)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.